Update README.md

README.md

@@ -1,9 +1,16 @@
+---
+license: mit
+pipeline_tag: object-detection
+---
 
 # Selective Contrastive Learning for Weakly Supervised Affordance Grounding (ICCV 2025)
 WonJun Moon*</sup>, Hyun Seok Seong*</sup>, Jae-Pil Heo</sup> (*: equal contribution)
 
-[[Arxiv](https://arxiv.org/abs/2508.07877)]
+[[Arxiv](https://arxiv.org/abs/2508.07877)] [[Github](https://github.com/hynnsk/SelectiveCL)]
+(Code will be released soon.)
+
+## Abstract
+> Facilitating an entity's interaction with objects requires accurately identifying parts that afford specific actions. Weakly supervised affordance grounding (WSAG) seeks to imitate human learning from third-person demonstrations, where humans intuitively grasp functional parts without needing pixel-level annotations. To achieve this, grounding is typically learned using a shared classifier across images from different perspectives, along with distillation strategies incorporating part discovery process. However, since affordance-relevant parts are not always easily distinguishable, models primarily rely on classification, often focusing on common class-specific patterns that are unrelated to affordance. To address this limitation, we move beyond isolated part-level learning by introducing selective prototypical and pixel contrastive objectives that adaptively learn affordance-relevant cues at both the part and object levels, depending on the granularity of the available information. Initially, we find the action-associated objects in both egocentric (object-focused) and exocentric (third-person example) images by leveraging CLIP. Then, by cross-referencing the discovered objects of complementary views, we excavate the precise part-level affordance clues in each perspective. By consistently learning to distinguish affordance-relevant regions from affordance-irrelevant background context, our approach effectively shifts activation from irrelevant areas toward meaningful affordance cues. Experimental results demonstrate the effectiveness of our method.
+
+
 
----
-license: mit
----