Preserving Localized Patch Semantics in VLMs

Abstract: Logit Lens has been proposed for visualizing tokens that contribute most to LLM answers. Recently, Logit Lens was also shown to be applicable in autoregressive Vision-LLMs (VLMs), where it illustrates the conceptual content of image tokens in the form of heatmaps, e.g., which image tokens are likely to depict the concept of cat in a given image. However, the visual content of image tokens often gets diffused to language tokens, and consequently, the locality of visual information gets mostly destroyed, which renders Logit Lens visualization unusable for explainability. To address this issue, we introduce a complementary loss to next-token prediction (NTP) to prevent the visual tokens from losing the visual representation inherited from corresponding image patches. The proposed Logit Lens Loss (LLL) is designed to make visual token embeddings more semantically aligned with the textual concepts that describe their image regions (e.g., patches containing a cat with the word "cat"), without requiring any architectural modification or large-scale training. This way, LLL constrains the mixing of image and text tokens in the self-attention layers in order to prevent image tokens from losing their localized visual information. As our experiments show, LLL not only makes Logit Lens practically relevant by producing meaningful object confidence maps in images, but also improves performance on vision-centric tasks like segmentation without attaching any special heads.