A new open-access landscape concept dataset enables the first application of Robust TCAV to deep learning species distribution models, validating predictions against expert knowledge and uncovering novel ecological associations for two aquatic insect groups.
In: International Conference on Learning Representations (2021)
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
RAS is a plug-and-play OOD detection technique that applies ranked activation shifts to a fixed reference profile for stable discrimination without hyperparameters.
TSegAgent achieves accurate zero-shot tooth segmentation on 3D dental scans via geometry-aware vision-language reasoning without task-specific training.
A noise-aware contrastive loss derived from temporal structure in colonoscopy videos produces polyp tracklet representations that outperform prior self-supervised and supervised baselines on retrieval, re-identification, size estimation, and histology tasks.
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.
Tunable MAGMAX adds a tunable preference vector to model merging for continual learning, enabling automatic adaptation to target environments using small amounts of data while maintaining or improving task-wise performance.
Systematic zero-shot benchmarking of open-source VLMs on multimodal grocery product retrieval shows data quality outperforms scale, introduces semantic power density as an efficiency metric, and identifies a persistent top-1 precision gap.
citing papers explorer
-
A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models
A new open-access landscape concept dataset enables the first application of Robust TCAV to deep learning species distribution models, validating predictions against expert knowledge and uncovering novel ecological associations for two aquatic insect groups.
-
Ranked Activation Shift for Post-Hoc Out-of-Distribution Detection
RAS is a plug-and-play OOD detection technique that applies ranked activation shifts to a fixed reference profile for stable discrimination without hyperparameters.
-
TSegAgent: Zero-Shot Tooth Segmentation via Geometry-Aware Vision-Language Agents
TSegAgent achieves accurate zero-shot tooth segmentation on 3D dental scans via geometry-aware vision-language reasoning without task-specific training.
-
Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
A noise-aware contrastive loss derived from temporal structure in colonoscopy videos produces polyp tracklet representations that outperform prior self-supervised and supervised baselines on retrieval, re-identification, size estimation, and histology tasks.
-
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.
-
Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
Tunable MAGMAX adds a tunable preference vector to model merging for continual learning, enabling automatic adaptation to target environments using small amounts of data while maintaining or improving task-wise performance.
-
What Matters for Grocery Product Retrieval with Open Source Vision Language Models
Systematic zero-shot benchmarking of open-source VLMs on multimodal grocery product retrieval shows data quality outperforms scale, introduces semantic power density as an efficiency metric, and identifies a persistent top-1 precision gap.