5 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those models are often limited to fixed categories or depend on language to define their concepts. We introduce DisParQ (Discrete Parts with Quant...
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. Annotation-free variants remove this requirement, but typically use large concept vocabularies, static at both training and inference, produci...
This work introduces anti-aliasing strategies using ASAP and BlurPool to significantly improve explanation quality and preserves strong predictive performance while providing faithful and artifact-free explanations suitable for clinical application in multi-class and multi-label settings.
The proposed LTTL combines the power of meta-learning and self-training, achieving superior performance compared with the baseline methods on two public benchmarks, and uses the meta-learning paradigm to optimize the parameters in the whole framework.
This work proposes TEVI, a framework that uses captions as a signal for what to retain from image embeddings and uses sparse autoencoders to disentangle image embeddings and train a masking module to selectively reconstruct the embedding based on a given caption.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
