DAPNet: Dual Adaptive Pyramid Network

Updated 11 July 2026

DAPNet is a dual adaptive pyramid network for unsupervised domain adaptation in histopathological gland segmentation that aligns both stain appearance and spatial features.
It integrates a pyramid-feature segmentation backbone with dual adversarial discriminators at image and feature levels to improve segmentation robustness under cross-stain shifts.
Empirical evaluations show significant improvements in pixel accuracy and IoU over baselines on datasets like Warwick-QU and GlandVision.

Searching arXiv for the exact DAPNet paper and closely related context papers. I’m checking for the exact arXiv entry and related domain-adaptation segmentation papers. DAPNet most commonly denotes the Dual Adaptive Pyramid Network, an unsupervised domain adaptation framework for semantic segmentation of histopathology images under cross-stain shift. It was introduced for gland segmentation when a model is trained on a labeled source stain and deployed on a visually different, unlabeled target stain, specifically in settings such as Hematoxylin & Eosin (H&E) versus Diaminobenzidene–Hematoxylin (DAB-H) stained colon tissue. Its central design combines a pyramid-feature segmentation backbone with dual adversarial domain classifiers operating at the image level and the feature level, so that global stain appearance and segmentation-relevant spatial structure are aligned simultaneously (Hou et al., 2019).

1. Problem formulation and domain-adaptation setting

DAPNet is formulated for unsupervised domain adaptation in histopathological gland segmentation, where the source domain $\mathcal{S}$ contains images $X_S$ with pixel-wise labels $Y_S$ , while the target domain $\mathcal{T}$ contains images $X_T$ with no labels (Hou et al., 2019). The objective is to train a segmentation model on $\mathcal{S}$ and obtain accurate gland segmentations on $\mathcal{T}$ without requiring new target annotations.

The motivation is the practical failure mode of supervised semantic segmentation under domain mismatch. In this setting, performance degradation arises from large color/style shifts, differences in texture and structural appearance, and variations in annotation protocols. The cited example is particularly stringent because Warwick-QU masks cover entire gland structures, whereas GlandVision masks label lumen regions only. DAPNet therefore addresses not only stain variation but also an annotation-regime discrepancy (Hou et al., 2019).

The framework treats adaptation at two levels. The image-level component targets differences in color and stain style. The feature-level component targets spatial inconsistency between domains, including gland layout, boundary appearance, and local context. This suggests that DAPNet is not a stain-normalization pipeline in the narrow sense; rather, it is a segmentation model whose intermediate representations are explicitly regularized toward domain invariance.

2. Segmentation backbone and pyramid representation

DAPNet consists of a segmentation network $G$ and two adversarial domain classifiers. The segmentation backbone is an encoder–decoder with pyramid features. Its encoder is a Dilated ResNet-18, modified with dilated convolutions to maintain spatial resolution and enlarge receptive field, using $3 \times 3$ convolutions with batch normalization (Hou et al., 2019).

On the encoder’s final layer, DAPNet inserts a Pyramid Pooling Module (PPM). The PPM applies pooling at multiple scales, upsamples the pooled representations back to the original feature-map resolution, and concatenates them into a global pyramid-pooled representation. In DAPNet this representation serves two roles simultaneously: it contributes to the segmentation pathway and also defines the image-level representation supplied to the image-level discriminator.

The decoder uses U-Net-style skip connections and pyramid feature fusion. Multi-scale decoded feature maps are upsampled to a common resolution and concatenated in a pyramidal way. A final $1 \times 1$ convolution reduces the fused feature map channel dimension to 512. This fused pre-classifier feature map is used both for the final segmentation classifier and for the feature-level discriminator (Hou et al., 2019).

The term “pyramid” therefore has a dual meaning in DAPNet. It refers to a downsampling pyramid, built from encoder features and the PPM, and to an upsampling pyramid, in which decoded multi-scale features are fused into a single representation. A plausible implication is that the architecture was designed so that adversarial alignment acts on already multi-scale, segmentation-oriented features rather than on a single-resolution latent state.

3. Dual adaptive mechanism: image-level and feature-level adversarial alignment

The defining property of DAPNet is its dual adaptive design. The first adaptive component is image-level adaptation through a discriminator $X_S$ 0 operating on the PPM outputs $X_S$ 1 and $X_S$ 2. These high-level global-context features are intended to capture color and style, and the goal is to make target PPM features indistinguishable from source PPM features. The image-level domain-classification loss is written as

$X_S$ 3

The discriminator is trained to distinguish source from target, while the segmentation network is trained adversarially to confuse it (Hou et al., 2019).

The second adaptive component is feature-level adaptation through a discriminator $X_S$ 4 operating on the fused pyramid feature maps $X_S$ 5 and $X_S$ 6 immediately before the segmentation classifier. These features encode global layout of glands, local context, and structural patterns relevant to segmentation. The feature-level domain-classification loss is

$X_S$ 7

Both $X_S$ 8 and $X_S$ 9 are implemented as PatchGAN discriminators, that is, fully convolutional classifiers producing per-patch domain predictions. This patch-wise formulation is important in histopathology because stain shift and structural mismatch are spatially heterogeneous rather than uniformly global. The paper describes image-level adaptation as modeling global differences in color, stain style, and overall appearance, whereas feature-level adaptation addresses spatial inconsistency and higher-level feature distribution mismatch such as gland layout and boundary appearance (Hou et al., 2019).

The two discriminators are complementary rather than redundant. The image-level branch acts on PPM representations that are still strongly tied to global style, while the feature-level branch acts on segmentation-specific fused features. This supports the paper’s interpretation that global appearance alignment and segmentation-level structural alignment should be optimized separately.

4. Objective function, optimization, and datasets

DAPNet is trained on labeled source images with a segmentation loss that combines cross-entropy and Dice terms:

$Y_S$ 0

with $Y_S$ 1 in the experiments. The full joint min–max objective is

$Y_S$ 2

with $Y_S$ 3 and $Y_S$ 4 (Hou et al., 2019).

Optimization uses Adam with learning rate $Y_S$ 5. Training lasts 300 epochs, with constant learning rate for the first 150 epochs and linear decay to 0 in the last 150. The batch size is 4, and training uses random crops of $Y_S$ 6. For the adversarial component, DAPNet uses LSGAN for improved stability and better quality feature alignment (Hou et al., 2019).

Evaluation uses two gland segmentation datasets. The Warwick-QU dataset from the MICCAI GlaS challenge contains 165 images cropped from WSIs at 20× magnification, split into 85 training and 80 test, with masks covering entire gland structures. The GlandVision dataset contains 20 DAB-H stained colon images of size $Y_S$ 7, acquired at 10× magnification, split into 14 training and 6 test, with masks labeling lumen regions only (Hou et al., 2019).

DAPNet is evaluated in both directions: Warwick-QU $Y_S$ 8 GlandVision and GlandVision $Y_S$ 9 Warwick-QU. In each case, the source domain provides images and labels, the target-domain training set is used without labels, and testing is performed on the target-domain test set. This bidirectional protocol is significant because the two directions are not symmetric: they differ in stain appearance, magnification, and label semantics.

5. Empirical performance, ablations, and qualitative behavior

The reported evaluation metrics are Pixel Accuracy (Acc.) and Intersection over Union (IoU) for the foreground. DAPNet is compared with CycleGAN, CyCADA, AdaptSeg, and three internal variants: DAPNet-NA (no adaptation), DAPNet-IA (image-level adaptation only), and DAPNet-FA (feature-level adaptation only) (Hou et al., 2019).

Method	Warwick-QU $\mathcal{T}$ 0 GlandVision	GlandVision $\mathcal{T}$ 1 Warwick-QU
CycleGAN	0.84 / 0.60	0.74 / 0.54
CyCADA	0.84 / 0.62	0.73 / 0.54
AdaptSeg	0.81 / 0.67	0.72 / 0.52
DAPNet-NA	0.80 / 0.58	0.73 / 0.50
DAPNet-IA	0.85 / 0.60	0.75 / 0.55
DAPNet-FA	0.83 / 0.63	0.74 / 0.53
DAPNet	0.88 / 0.68	0.76 / 0.57

The full model outperforms all baselines in both transfer directions. Training repeated 3 times with random initialization yields statistically significant improvements by paired $\mathcal{T}$ 2-test with $\mathcal{T}$ 3. The reported averages for the full model are $\mathcal{T}$ 4 Acc. and $\mathcal{T}$ 5 IoU for Warwick-QU $\mathcal{T}$ 6 GlandVision, and $\mathcal{T}$ 7 Acc. and $\mathcal{T}$ 8 IoU for GlandVision $\mathcal{T}$ 9 Warwick-QU (Hou et al., 2019).

The ablation study isolates the contribution of the two adaptation levels. DAPNet-NA exhibits a substantial performance drop, indicating strong domain shift. DAPNet-IA improves over the non-adaptive baseline by addressing color and style mismatch, while DAPNet-FA improves alignment of segmentation features and yields stronger IoU than image-level adaptation alone in the Warwick-QU $X_T$ 0 GlandVision direction. The full DAPNet performs best, which the paper interprets as evidence of complementarity between image-level and feature-level adaptation.

Qualitative comparisons describe CycleGAN and CyCADA outputs as containing irregular spot noise and fragmented boundaries, while AdaptSeg struggles with clear gland boundaries and may under-segment or miss structures. DAPNet is reported to produce cleaner masks, more accurate gland shapes, clear boundaries, and less noisy predictions, particularly in difficult cases where stain differences distort appearance. Additional analysis shows that target-domain IoU improves with adaptation modules while source-domain performance remains high and stable, indicating that adaptation does not significantly harm source-domain accuracy (Hou et al., 2019).

6. Interpretation, limitations, and position within the literature

DAPNet occupies a specific position within domain-adaptive medical image segmentation. Relative to domain-adversarial training, it uses two separate discriminators at different representation levels. Relative to pixel-level translation approaches such as CycleGAN and CyCADA, it avoids explicit image translation and instead aligns feature-space representations at image and segmentation levels. Relative to structured output adaptation such as AdaptSeg, it places the adversarial constraint on internal segmentation features rather than only on final outputs. The paper also situates the architecture alongside work emphasizing feature-based alignment plus multi-level adaptation, citing “Synergistic Image and Feature Adaptation” as a related direction (Hou et al., 2019).

Several limitations are either stated or directly implied. The paper does not explicitly enumerate many failure modes, but the described setup suggests possible difficulty under extreme stain variation, under very small or complex structures, and when annotation semantics diverge more severely than the whole gland versus lumen-only discrepancy studied here. Generalization to other organs, stains, or imaging modalities is presented as plausible but is not empirically demonstrated in the reported experiments. The adversarial formulation also introduces the usual sensitivity of GAN-based optimization to hyperparameter choices such as $X_T$ 1, $X_T$ 2, and learning rate.

In practical terms, DAPNet is presented as a way to reuse and adapt models trained under one staining protocol to another with no target-domain labels, potentially reducing the need for stain-specific annotation and supporting more robust multi-center deployment. This suggests a broader relevance to pathology workflows in which scanner protocols, stain chemistry, and annotation conventions vary across institutions.

The acronym DAPNet is not unique in the arXiv literature. It also refers to “Deep Adaptive Proposal Network” for optical remote sensing object detection (Cheng et al., 2018), “DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling” (Chen et al., 2020), and “Dynamic Adaptive Parsing of Temporal and Cross-Variable Patterns for Network State Classification” (Gao et al., 15 Sep 2025). In the context of histopathology and cross-stain gland segmentation, however, DAPNet specifically denotes the Dual Adaptive Pyramid Network introduced for unsupervised stain-domain adaptation (Hou et al., 2019).