# CASTing Your Model: Learning to Localize Improves Self-Supervised Representations Source: [CASTing Your Model: Learning to Localize Improves Self-Supervised Representations]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:45.779Z Authors: Ramprasaath R. Selvaraju, Karan Desai, Justin Johnson, Nikhil Naik Published: 2020-12-08T18:50:18.000Z ## Abstract Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when trained on larger sets of uncurated images. We hypothesize that current SSL methods perform best on iconic images, and struggle on complex scene images with many objects. Analyzing contrastive SSL methods shows that they have poor visual grounding and receive poor supervisory signal when trained on scene images. We propose Contrastive Attention-Supervised Tuning(CAST) to overcome these limitations. CAST uses unsupervised saliency maps to intelligently sample crops, and to provide grounding supervision via a Grad-CAM attention loss. Experiments on COCO show that CAST significantly improves the features learned by SSL methods on scene images, and further experiments show that CAST-trained models are more robust to changes in backgrounds. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()