Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Towards Realistic Predictors - EN

Leszek Rybicki
November 29, 2018

Towards Realistic Predictors - EN

Later version of the "Towards Realistic Predictors" paper review, in English.

Leszek Rybicki

November 29, 2018
Tweet

More Decks by Leszek Rybicki

Other Decks in Research

Transcript

  1. Towards Realistic Predictors Pei Wang and Nuno Vasconcelos Statistical and

    Visual Computing Lab, UC San Diego mlKitchen X 2018.11.29 @_lunardog_ http://openaccess.thecvf.com/content_ECCV_2018/papers/Pei_Wang_Towards_Realistic_Predictors_ECCV_2018_paper.pdf
  2. Self-Introduction • Call me Leszek • Born in Poland •

    Living in Japan since 2010 • Cookpad R&D since 2016 • I consume too much science fiction • I’m bad at selfies
  3. Towards Realistic Predictors Pei Wang and Nuno Vasconcelos Statistical and

    Visual Computing Lab, UC San Diego http://openaccess.thecvf.com/content_ECCV_2018/papers/Pei_Wang_Towards_Realistic_Predictors_ECCV_2018_paper.pdf
  4. Hardness Predictor Loss bi y s e t y s

    u w r e s ma c mi zi t K l a k-Le b di g e b en t di r i n d a m i m n = 1 − p c
  5. Classifier Loss weighted by hardness we t ro -en p

    ma h er p e (la r ) mo po n , w i as e m s (lo s) ar en s or c
  6. Classifier HP-Net Training 1. train classifier F and HP-Net S

    jointly on training set D 2. run S on D and eliminate hard examples, to create realistic training set D′ 3. learn realistic classifier F′ on D′, with S fixed 4. output pair S, F′ 5. GOTO 1 D F S
  7. C - normal classifier F - realistic predictor without fine-tuning

    (just rejection) F’ - realistic predictor, fine-tuned on samples accepted by HP-Net
  8. Conclusions • There are times when it’s OK to skip

    hard samples • ...and times when it’s BEST to reject hard samples • The paper introduces a GAN-like architecture to train any classifier with its own hardness predictor • Training with a hardness predictor improves accuracy • HP-Net should be trained jointly with the classifier, but in an alternating order • HP-Net solves a different problem from the Classifier, should be a separate model • ….but best results are when the architectures are the same
  9. https://ja.wikipedia.org/wiki/2001年宇宙の旅    うちゅうのたび 2001年宇宙の旅 『2001年宇宙の旅』(にせんいちねんう ちゅうのたび、原題:2001: A Space Odyssey)は、アーサー・C・クラークとスタン リー・キューブリックのアイデアをまとめた ストーリーに基いて製作された、SF映画お

    よびSF小説である。 2001: A Space Odyssey is a 1968 epic science fiction film produced and directed by Stanley Kubrick. The screenplay was written by Kubrick and Arthur C. Clarke, and was inspired by Clarke's short story "The Sentinel". A novel also called 2001: A Space Odyssey, written concurrently with the screenplay, was published soon after the film was released. 2001: A Space Odyssey https://en.wikipedia.org/wiki/2001:_A_Space_Odyssey_(film)
  10. Fra Dav HA 9000 is r pe in f e

    n a om d i n p e h Frank and Dave don’t trust HAL. HAL is a realistic predictor and doesn’t always follow orders.