AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

On the Faithfulness of Post-Hoc Concept Bottleneck Models

Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Concept bottleneck models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train the concept projection on out-of-distribution data instead of in-domain data (ablation)PCBM · Elements (post-hoc CBM)downstream accuracy with oracle h*: 1.00 -> 0.21Hurt
train the concept projection on out-of-distribution data instead of in-domain data (ablation)PCBM · Elements (post-hoc CBM)concept direction cosine similarity: 0.96 -> 0.47Hurt
train the concept projection on out-of-distribution data instead of in-domain data (ablation)PCBM · Elements (post-hoc CBM)downstream accuracy with learned h: 1.00 -> 1.00No clear effect
train on near-domain P_near^forall instead of in-domain data (ablation)PCBM · Elements (post-hoc CBM)concept accuracy on P_task: 1.00 -> 0.70Hurt
use CLIP surrogate labels instead of 25% random-noise labels (ablation)LFCBM · Elements (post-hoc CBM)concept accuracy on P_task: 0.98 -> 0.56Hurt
use DINOv3 instead of CLIP for surrogate labelsLFCBM · Elements (post-hoc CBM)downstream accuracy with oracle h*: 0.54 -> 0.78Improved
use Grounding DINO surrogate labels instead of 25% noise (ablation)VLG-CBM · Elements (post-hoc CBM)downstream accuracy with oracle h*: 0.98 -> 0.04Hurt
use learned classifier h instead of oracle h*LFCBM with CLIP labels · Elements (post-hoc CBM)downstream accuracy: 0.54 -> 0.99Mixed
increase number of random concept projections K (ablation)post-hoc CBM with random projections · Elements (post-hoc CBM)downstream accuracy (CIFAR-100)Improved
replace random projections with meaningful concept sourcespost-hoc CBM · Elements (post-hoc CBM)downstream accuracy (CIFAR-100)No clear effect
use Grounding DINO instead of CLIP or DINOv3 for surrogate labelssurrogate labeling · Elements (post-hoc CBM)mean absolute error-activation correlation: 0.152 -> 0.142Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy