AI Paper Atlas

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

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

Simon Vandenhende, Dhruv Mahajan, Filip Radenovic, Deepti Ghadiyaram

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 37 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
add semantic consistency loss (ablation)visual counterfactuals (VGG-16) · CUBSame-KP: 8.3 -> 22.0Improved
add semantic consistency loss (ablation)visual counterfactuals (VGG-16) · CUBNear-KP: 54.6 -> 52.1 (-2.5)Hurt
add semantic consistency loss (ablation)visual counterfactuals (VGG-16) · CUB#Edits: 5.5 -> 6.8Hurt
add multiple distractor images (ablation)visual counterfactuals (VGG-16) · CUBNear-KP: 54.6 -> 65.6 (+11.0)Improved
add multiple distractor images (ablation)visual counterfactuals (VGG-16) · CUBruntime (s): 0.81 -> 9.98Hurt
add semantic loss on top of multiple distractors (ablation)visual counterfactuals (VGG-16) · CUBSame-KP: 13.8 -> 36.0Improved
add cell pre-filtering (ablation)visual counterfactuals (VGG-16) · CUBruntime (s): 10.82 -> 1.15Improved
add cell pre-filtering (ablation)visual counterfactuals (VGG-16) · CUBSame-KP: 36.0 -> 35.3No clear effect
use self-supervised DeepCluster instead of CUB classifier as auxiliary model (ablation)semantic loss · CUBSame-KP: 10.1 -> 22.0Improved
use ImageNet-1k supervised classifier instead of CUB classifier as auxiliary model (ablation)semantic loss · CUBSame-KP: 10.1 -> 19.3Improved
use SWAV instead of MoCo as auxiliary model (ablation)semantic loss · CUBSame-KP: 18.1 -> 22.1Improved
use our counterfactuals instead of Goyal et al. for human teaching with semantically-consistent pairsmachine teaching · CUBtest accuracy (%): 64.3 -> 82.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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