Grad-ECLIP produces gradient-based visual and textual explanation heatmaps for CLIP by applying channel and spatial weights to token features instead of relying on sparse self-attention maps.
Grad-cam: Visual explanations from deep networks via gradient-based localization,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
EDFL improves visible-thermal person re-identification by enhancing feature discriminability with skip connections and dual-modality triplet loss, outperforming state-of-the-art on two datasets.
citing papers explorer
-
Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP
Grad-ECLIP produces gradient-based visual and textual explanation heatmaps for CLIP by applying channel and spatial weights to token features instead of relying on sparse self-attention maps.
-
Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
EDFL improves visible-thermal person re-identification by enhancing feature discriminability with skip connections and dual-modality triplet loss, outperforming state-of-the-art on two datasets.